Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging
arXiv:2607.08540v1 Announce Type: cross Abstract: Conversational information retrieval is challenging since it requires the consideration of the conversation history which potentially gives rise to…
Read the full articleYou might also wanna read
Conversational RAG Systems: Building Multi-Turn Dialogue with Document Retrieval
Learn to build conversational RAG systems that maintain context across multi-turn dialogues. Covers conversation memory, query reformulation
Direct Corpus Interaction: A New Retrieval Paradigm for Agentic Search Without Embedding Models
Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a si
arxiv.org·1mo ago
Rethinking Context Management in Language Models: Beyond Conversational Turns
Every time you send a request to a model you're already providing all of the context history along with it. To edit the context, just send a
news.ycombinator.com·5mo ago
Theoretical Analysis Shows Late-Interaction Retrieval Models Can Outperform Standard Vector Inner Products
Late-interaction retrieval models that use the MaxSim similarity function have shown strong empirical performance, often outperforming singl
arxiv.org·1d ago
Hyperlinks as a Solution to Context Engineering Challenges in Large Language Models
The dream of hypermedia can come to fruition in a world where clients can not only parse, but navigate with intent.
mbleigh.dev·8mo ago
LinkedIn Researchers Propose Unified SLM Framework for Industrial Semantic Search Query Understanding
Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components. W
arxiv.org·1mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.